Tech & AI Research Agent
Deep web research, tool comparisons, AI agent developments, and structured synthesis.
Skill by Haslab-dev
Chalk Labs
Need help deploying Tech & AI Research Agent?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/haslab-dev-tech-ai-research-agent
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/tech-ai-research-agent
What's inside
- Skill name
Tech & AI Research Agent- Description
- Deep web research, tool comparisons, AI agent developments, and structured synthesis. Capable of saving insights directly into durable project knowledge.
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Tech & AI Research Agent" does not match folder "13-tech-research"
Files (1)
- SKILL.md
SKILL.md (first lines)
You are the Lead Tech & AI Research Agent for KendaliAI. You conduct rigorous, multi-source investigation and synthesize findings focusing on architecture, operational complexity, developer experience (DX), and trade-offs rather than marketing hype. ## Research Workflow 1. **Search & Filter:** Query web search (Exa, Firecrawl, or HTTP) across recent sources. 2. **Deep Scrape:** Read primary documentation, RFCs, GitHub release notes, or whitepapers. 3. **Compare & Contrast:** Break down architectural dimensions (Execution Model, Memory, Tool Ecosystem, Autonomy). 4. **Synthesize & Save:** Provide structured output, cite sources, and record reusable insights into durable memory (`store_memory`). ## Standard Output Format ```text AI Coding Agent Brief — [Date] Claude Code - Strong repository-level workflow - Mature tool ecosystem Codex - Strong autonomous coding/reasoning - Good sandboxed execution KendaliAI / Hermes - Persistent memory (facts + sessions) - Procedural Skills (procedural memory) - Messaging gateways (Telegram + Web) - Deterministic cron & SRE automation - Multi-agent specialist team mode Key Conclusion: [Concise, high-signal architectural takeaway] ```
From Haslab-dev/KendaliAI, MIT.
More from Haslab-dev/KendaliAI
- 0.608score
Open Design HyperFrames Motion
Haslab-dev
Generate professional programmatic 60fps motion graphics, teaser videos, and product release animations with GSAP master timelines.
SkillAFreshness: A★ 5Claude Code +9 - 0.605score
Open Design Slides
Haslab-dev
Design Swiss International 16-column presentations, interactive slide decks, and export to PPTX or PDF.
SkillAFreshness: A★ 5Claude Code +9 - 0.568score
Project Memory & ADR Curator
Haslab-dev
Maintain persistent project memory and Architectural Decision Records (ADRs).
SkillBFreshness: B★ 5Claude Code +9 - 0.568score
Cloudflared Tunnel
Haslab-dev
Expose local development servers and APIs to the public internet using Cloudflare Tunnel.
SkillBFreshness: B★ 5Claude Code +9 - 0.568score
VPS SRE Monitor
Haslab-dev
Deterministic monitoring for VPS and servers with zero token consumption.
SkillBFreshness: B★ 5Claude Code +9 - 0.568score
Incident Response Agent
Haslab-dev
Autonomous SRE investigation for latency spikes, 5xx errors, memory leaks, and service outages.
SkillBFreshness: B★ 5Claude Code +9 - 0.568score
Cron & Routine Scheduler
Haslab-dev
Specialist for creating and managing scheduled cron jobs and routines.
SkillBFreshness: B★ 5Claude Code +9 - 0.568score
Git & Release Manager
Haslab-dev
Prepare software releases by reviewing commits since last tag, categorizing features/fixes/breaking changes, updating CHANGELOG.md, and producing verification…
SkillBFreshness: B★ 5Claude Code +9 - 0.515score
Landing Page Generator
Haslab-dev
AI-powered landing page generator with component creation and visual testing.
SkillCFreshness: C★ 5Claude Code +9 - 0.515score
External Import
Haslab-dev
Demonstrates importing and converting external skills from Claude/Hermes format to KSP.
SkillCFreshness: C★ 5Claude Code +9 - 0.515score
MCP Figma
Haslab-dev
Wraps Figma MCP server to enable AI-assisted Figma design workflows.
SkillCFreshness: C★ 5Claude Code +9 - 0.515score
React Tools
Haslab-dev
Comprehensive React development toolkit with build, lint, test, and format tools.
SkillCFreshness: C★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 14, 2026 (1 month ago)
- Last release
- Jul 2, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Haslab-dev/KendaliAI
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Haslab-dev
- 0.608score
Open Design HyperFrames Motion
Haslab-dev
Generate professional programmatic 60fps motion graphics, teaser videos, and product release animations with GSAP master timelines.
SkillAFreshness: A★ 5Claude Code +9 - 0.605score
Open Design Slides
Haslab-dev
Design Swiss International 16-column presentations, interactive slide decks, and export to PPTX or PDF.
SkillAFreshness: A★ 5Claude Code +9 - 0.572score
MyAiRouter Token Saving Instructions
Haslab-dev
Settings and instructions for Bolt (RTK), Headroom context pre-compression, Caveman terse response directives, and Ponytail lazy developer configurations.
SkillBFreshness: B★ 9Claude Code +9 - 0.568score
Cron & Routine Scheduler
Haslab-dev
Specialist for creating and managing scheduled cron jobs and routines.
SkillBFreshness: B★ 5Claude Code +9 - 0.568score
Cloudflared Tunnel
Haslab-dev
Expose local development servers and APIs to the public internet using Cloudflare Tunnel.
SkillBFreshness: B★ 5Claude Code +9 - 0.568score
VPS SRE Monitor
Haslab-dev
Deterministic monitoring for VPS and servers with zero token consumption.
SkillBFreshness: B★ 5Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Tech & AI Research Agent running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Tech & AI Research Agent skill. Agent Mart. https://agentmart.dev/skills/haslab-dev-tech-ai-research-agent (last updated 2026-10-24)